# Zero Shot Composed Image Retrieval

arXiv: https://arxiv.org/abs/2506.06602 · HTML: https://mlsanity.com/paper/2506.06602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 7 Jun 2025.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion](https://mlsanity.com/paper/2303.11916/) (2023)
- [Compositional Learning of Image-Text Query for Image Retrieval](https://mlsanity.com/paper/2006.11149/) (2020)
- [InfoNCE: Identifying the Gap Between Theory and Practice](https://mlsanity.com/paper/2407.00143/) (2024)
- [Target-Guided Composed Image Retrieval](https://mlsanity.com/paper/2309.01366/) (2023)
- [iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2405.02951/) (2024)

## Abstract (arXiv)

Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text with separate pretrained vision-language encoders, reaches only 20-25% Recall@10 on the FashionIQ benchmark. We improve this by fine-tuning BLIP-2 with a lightweight Q-Former that fuses visual and textual features into a single embedding, raising Recall@10 to 45.6% (shirt), 40.1% (dress), and 50.4% (top-tee) and increasing the average Recall@50 to 67.6%. We also examine Retrieval-DPO, which fine-tunes CLIP's text encoder with a Direct Preference Optimization loss applied to FAISS-mined hard negatives. Despite extensive tuning of the scaling factor, index, and sampling strategy, Retrieval-DPO attains only 0.02% Recall@10 -- far below zero-shot and prompt-tuned baselines -- because it (i) lacks joint image-text fusion, (ii) uses a margin objective misaligned with top-K metrics, (iii) relies on low-quality negatives, and (iv) keeps the vision and Transformer layers frozen. Our results show that effective preference-based CIR requires genuine multimodal fusion, ranking-aware objectives, and carefully curated negatives.